Upload tokenizer_config.json with huggingface_hub

tokenizer_config.json

@@ -8,34 +8,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "250680": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "250681": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "bos_token": "<|im_start|>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{{ system_message }}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% elif (message['role'] == 'assistant') != (loop.index0 % 2 == 1) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{'\n\n' + 'Human: ' + message['content']}}{% elif message['role'] == 'assistant' %}{{'\n\n' + 'Assistant: ' + message['content']}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] == 'user' %}{{ '\n\n' + 'Assistant:' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "pad_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }